Mathematics Colloquia and Seminars

Return to Colloquia & Seminar listing

A novel approach to describe the variability of the statistics of intracranial EEG (icEEG) data is proposed that is an adaptation of the diffusion map framework. Diffusion maps, which extend principal components analysis and provide a nonlinear approach, provide dimensionality reduction of the data as well as pattern recognition that can be used to distinguish different states of a patient, for example, interictal and preseizure states. A new algorithm, which is an extension of diffusion maps, is developed to construct coordinates that generate efficient geometric representations of the complex structures in the icEEG data. This method is adapted to the icEEG data and enables the extraction of the underlying brain activity to identify preseizure states. The algorithm is tested on icEEG data recorded from several electrode contacts in one epilepsy patient. Numerical results show that the proposed approach provides a distinction between interictal and preseizure states. Furthermore, the algorithm is also currently applied to classify magnetic resonance images (MRI) of brains of patients with Alzheimer’s Disease and those without Alzheimer’s Disease. The method is adapted to the MRI and accounts for the variability in calibration of the MRI of different patients.